Build something useful with AI.

Start with a small job. Learn how agents work, set up OpenClaw, and follow practical exercises with results you can check.

The OpenClaw lobster logo on an ivory pedestal reached by three steps.
Start with OpenClawOpenClaw

From a fresh installation to an agent you can message. Install OpenClaw, connect Telegram, and learn what its permissions actually control.

Explore guide3 lessons · Beginner

All resources

12 results
Make sense of AI agents
AI lettering and a document-to-result sequence in ivory and red on navy.
Agentic AITrack

Make sense of AI agents

Understand how agents work, give one a useful job, and test its boundaries. Three lessons built around a single practical example.

3 lessons
Your first OpenClaw setup
The OpenClaw lobster logo on an ivory pedestal reached by three steps.
OpenClawTrack

Your first OpenClaw setup

From a fresh installation to an agent you can message. Install OpenClaw, connect Telegram, and learn what its permissions actually control.

3 lessons
Design skills for AI agents: sites that don't look AI-made
Three ivory cards fanned out on navy, marked with a vermilion motion curve, text lines and a layout grid, with a vermilion cursor resting on the front card.
Agentic AITutorial

Design skills for AI agents: sites that don't look AI-made

Install Emil Kowalski's skills, Impeccable and Taste, then connect the Figma and Playwright MCPs so Claude Code, Codex or Cursor designs, builds, tests and screenshots its own work.

20 min
TradingAgents: an AI trading desk on your computer
Six ivory seats around one vermilion oval table seen from above, a small report card at each seat, on navy.
Agentic AITutorial

TradingAgents: an AI trading desk on your computer

Install TradingAgents, pick a model and a ticker, and read how its analyst, researcher, trader and risk agents reach a decision. Open source and free to run.

25 min
OmniRoute: free AI quotas in Claude Code and Codex
Ivory discs connected by tubes to one vermilion hub, which feeds a single ivory capsule, on navy.
Agentic AITutorial

OmniRoute: free AI quotas in Claude Code and Codex

Install OmniRoute, connect free providers, and use them straight from Claude Code and Codex, with automatic fallback and token savings.

20 min
What an agent actually is
A red processor inside an ivory decision loop, with a document entering the cycle.
Agentic AIGuide

What an agent actually is

Understand the decision loop, choose a concrete job, and define where a person stays in control.

8 min
Tools, memory, and handoffs
A wrench, a stack of memory cards, and an arrow leading to a review tray.
Agentic AIGuide

Tools, memory, and handoffs

Choose a small tool set, decide what to remember, and make unfinished work easy for a person to pick up.

10 min
Design your first worker
Modular blocks assembling into a small worker beside a three-item test checklist.
Agentic AITutorial

Design your first worker

Write a delivery-reply brief and test it with three examples. A practical exercise before connecting real tools.

15 min
50 practical jobs for an AI agent
Large number 50 with an envelope, calendar, document, and checked task on navy.
Agentic AIList

50 practical jobs for an AI agent

Ideas for work, everyday life, and learning—with a clear output to review. Choose one small job and make it useful.

10 min
Install and run OpenClaw
OpenClaw lobster logo with the words Install. Connect. Run.
OpenClawTutorial

Install and run OpenClaw

Set up your own AI agent, connect a provider, and get your first reply. A practical guide from installation to a working chat.

25 min
Connect your first channel
A phone and chat bubbles connected by a red cable to the OpenClaw logo.
OpenClawGuide

Connect your first channel

Set up a Telegram bot, approve your account, and verify a reply on your phone. Includes paths for Discord and WhatsApp.

15 min
Permissions and your first task
An ivory shield with a red keyhole beside the OpenClaw logo and a checked task.
OpenClawTutorial

Permissions and your first task

Inspect access, set a deliberate command policy, and check the result of a small task against its activity.

12 min